FasterTransformer Creator Forks TokenSpeed as LLM Inference Stack Era Turns Over

zhyncs42 · x · 2026-09-07

zhyncs42 notes the creator of FasterTransformer has forked TokenSpeed and is preparing a PR. Just three years ago there was no vLLM or LMDeploy — everyone was reading the Orca paper trying to get continuous batching working on FasterTransformer. "Feels like a different era."

Original post →

More from Companies & People

Companies & People channel →